Share Email Print
cover

Proceedings Paper

Nanophotonic particle simulation and inverse design using artificial neural networks
Author(s): John Peurifoy; Yichen Shen; Li Jing; Yi Yang; Fidel Cano-Renteria; Brendan Delacy; Max Tegmark; John D. Joannopoulos; Marin Soljačić
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find the network needs to be trained on only a small sampling of the data in order to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used solve nanophotonic inverse design problems by using back-propogation - where the gradient is analytical, not numerical.

Paper Details

Date Published: 23 February 2018
PDF: 6 pages
Proc. SPIE 10526, Physics and Simulation of Optoelectronic Devices XXVI, 1052607 (23 February 2018); doi: 10.1117/12.2289195
Show Author Affiliations
John Peurifoy, Massachusetts Institute of Technology (United States)
Yichen Shen, Massachusetts Institute of Technology (United States)
Li Jing, Massachusetts Institute of Technology (United States)
Yi Yang, Massachusetts Institute of Technology (United States)
Fidel Cano-Renteria, Massachusetts Institute of Technology (United States)
Brendan Delacy, U.S. Army Edgewood Chemical Biological Ctr. (United States)
Max Tegmark, Massachusetts Institute of Technology (United States)
John D. Joannopoulos, Massachusetts Institute of Technology (United States)
Marin Soljačić, Massachusetts Institute of Technology (United States)


Published in SPIE Proceedings Vol. 10526:
Physics and Simulation of Optoelectronic Devices XXVI
Bernd Witzigmann; Marek Osiński; Yasuhiko Arakawa, Editor(s)

© SPIE. Terms of Use
Back to Top